tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : use n_swa + n_ubatch cells for SWA cache (#13833)

Browse Source 
* llama : use n_swa + n_ubatch cells for SWA cache

ggml-ci

* llama : add warning about multi-sqeuence SWA contexts
This commit is contained in:
Georgi Gerganov
2025-05-31 15:57:44 +03:00
committed by GitHub
parent c7e0a2054b
commit 3600cc2886
6 changed files with 24 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
tools/server/server.cpp
View File

@ -2016,11 +2016,6 @@ struct server_context {
params_base.n_cache_reuse = 0;
SRV_WRN("%s\n", "cache_reuse is not supported by this context, it will be disabled");
}
if (!params_base.speculative.model.path.empty()) {
SRV_ERR("%s\n", "err: speculative decode is not supported by this context");
return false;
}
}
return true;
@ -3215,8 +3210,14 @@ struct server_context {
if (slot.n_past > 0 && slot.n_past < (int) slot.cache_tokens.size()) {
const auto pos_min = llama_kv_self_seq_pos_min(ctx, slot.id);
if (pos_min > 0) {
SLT_WRN(slot, "n_past = %d, cache_tokens.size() = %d, seq_id = %d, pos_min = %d\n", slot.n_past, (int) slot.cache_tokens.size(), slot.id, pos_min);
if (pos_min == -1) {
SLT_ERR(slot, "n_past = %d, cache_tokens.size() = %d, seq_id = %d, pos_min = %d\n", slot.n_past, (int) slot.cache_tokens.size(), slot.id, pos_min);
GGML_ABORT("pos_min == -1, but n_past > 0 - should not happen: https://github.com/ggml-org/llama.cpp/pull/13833#discussion_r2116181237");
}
const auto n_swa = llama_model_n_swa(model);
if (pos_min > slot.n_past - n_swa) {
SLT_WRN(slot, "n_past = %d, cache_tokens.size() = %d, seq_id = %d, pos_min = %d, n_swa = %d\n", slot.n_past, (int) slot.cache_tokens.size(), slot.id, pos_min, n_swa);
SLT_WRN(slot, "forcing full prompt re-processing due to lack of cache data (likely due to SWA, see %s)\n",
"https://github.com/ggml-org/llama.cpp/pull/13194#issuecomment-2868343055");
llama_kv_self_seq_rm(ctx, slot.id, 0, -1);